{"slug":"topaz-denoise-ai-guide","title":"强力降噪同时保留细节！人工智能降噪插件Topaz Denoise AI教程","author":"Thomas看看世界","date":"2020-08-16","wechat":"https://mp.weixin.qq.com/s?__biz=MzI4NDA5MzE5NQ==&mid=2247491150&idx=1&sn=e9466bde7b8a0214a8c22a8b665faefd&chksm=eb81e02adcf6693c9a5e779315883d65a6f1f46545ec347c3dc3a71f1a3802bb8b094ae1056e&scene=21#wechat_redirect","blocks":[{"t":"h","x":"Thomas看看世界","xe":"Thomas Chu Photo"},{"t":"p","x":"在两周前的文章《7万高ISO也能出大片？这个降噪技术太厉害了！》中，野生动物摄影师杰夫分享了他的降噪流程，其中最重要的就是Topaz Denoise AI这个插件的使用。","b":false,"xe":"In the article two weeks ago, \"Great Shots at ISO 70,000? This Noise Reduction Tech Is Incredible!\", wildlife photographer Jeff shared his noise reduction workflow, in which the Topaz DeNoise AI plugin plays the key role."},{"t":"p","x":"这个插件究竟有何神奇之处？如何使用这个插件？本周的教程托马斯就会和大家详细讲解和演示。","b":false,"xe":"What makes this plugin so magical, and how do you use it? In this week's tutorial, Thomas explains and demonstrates it in detail."},{"t":"h","x":"视频教程","xe":"Video Tutorial"},{"t":"bili","bv":"BV1gk4y127Hb","bpic":"bili-1","bt":"人工智能降噪神器！Topaz Denoise AI照片降噪教程"},{"t":"p","x":"这一篇是上面视频的图文整理。Thomas 完整演示了人工智能降噪插件 Topaz Denoise AI 的获取安装、降噪前的 Camera Raw 准备工作、插件内部的模式选择与滑块调整，以及锐化、恢复原始细节、低光模式等进阶选项，并配有关键帧截图，方便对照上手。","xe":"This is the fully illustrated companion to the video above. Thomas walks through the AI noise-reduction plugin Topaz Denoise AI end to end — purchase and installation, the Camera Raw preparation before denoising, the plugin's modes and sliders, plus advanced options like sharpening, Recover Original Detail and Low Light Mode — with keyframe screenshots for easy follow-along.","b":false},{"t":"p","x":"先看插件全貌。进入插件后，右侧面板就是全部核心：上方是 Denoise AI / AI Clear 两种模式，中间是 Remove Noise（降噪）与 Sharpen（锐化）两个滑块，以及 Auto 自动分析按钮，下方还有 Post Processing 与低光模式等选项（视频 5:20 处）。下面逐一展开。","xe":"Start with the plugin at a glance: once inside, the right panel holds everything — the Denoise AI / AI Clear modes up top, the Remove Noise and Sharpen sliders plus the Auto analysis button in the middle, and Post Processing and Low Light Mode below (at 5:20 in the video). Each is unpacked below.","b":false},{"t":"img","f":"v07","w":768,"h":480},{"t":"h","x":"01 获取与安装：官网购买或淘宝汉化","xe":"01 Getting and Installing: Official Site or Taobao"},{"t":"p","x":"Topaz Denoise AI 可以在官网购买，价格 79.9 美金；也可以直接点 Download Trial 下载试用版，有 30 天试用期（视频 0:32 处）。如果访问外网不方便，在淘宝、百度也能找到汉化版本或和谐版本。","xe":"Topaz Denoise AI sells on its official site for $79.9; you can also hit Download Trial for a 30-day free trial (at 0:32 in the video). If the site is hard to reach from your network, localized (or cracked) copies can be found via Taobao and Baidu.","b":false},{"t":"img","f":"v02","w":768,"h":480},{"t":"p","x":"安装之后，插件会出现在 PS 的「滤镜 → Topaz Labs」菜单里，同时桌面也会生成一个独立程序——不过一般来说，我们都在 PS 里面调用它（视频 0:51 处）。","xe":"After installation the plugin appears under Photoshop's Filter → Topaz Labs menu, with a standalone program on the desktop as well — though in practice you will almost always call it from inside Photoshop (at 0:51 in the video).","b":false},{"t":"h","x":"02 降噪之前：Camera Raw 里的准备工作","xe":"02 Before Denoising: Preparation in Camera Raw"},{"t":"p","x":"视频里的案例照片拍摄于 ISO3200、严重欠曝、1/40 秒——为了抓住人物动感不得不如此（视频 1:04 处）。降噪前的第一步，是在 Adobe Camera Raw 里恢复曝光、提升阴影、降低高光：只有先把欠曝的暗部提上来，需要处理的噪点才会显现出来（1:24-1:41 处）。","xe":"The demo photo was shot at ISO 3200, severely underexposed, at 1/40 s — forced by the need to freeze the person's movement (at 1:04 in the video). Step one before denoising: in Adobe Camera Raw, restore the exposure, lift the shadows and pull the highlights down — only when the dark tones come up do the noisy areas you need to treat become visible (at 1:24-1:41 in the video).","b":false},{"t":"img","f":"v03","w":768,"h":480},{"t":"p","x":"注意 Camera Raw「细节」面板里的颜色降噪默认是 25，它一直在做颜色噪点的消除，而且做得相当不错，保持默认即可（视频 1:43 处）。但如果接下来要在插件里降噪，「减少杂色（明亮度）」一定要归零——它会把噪点提前降掉，而且细节保护并不好。另一个通用规则：降噪是后期的第一步，锐化是最后一步，中间不要提前做清晰度、去污这类会强化噪点的操作（2:33-2:58 处）。","xe":"Note that in Camera Raw's Detail panel, Color Noise Reduction defaults to 25 — it quietly removes color noise all the time and does it well, so leave it (at 1:43 in the video). But if a plugin pass is coming, set Luminance Noise Reduction to zero — it would pre-crush the noise with poor detail protection. Another universal rule: denoise first, sharpen last, and in between avoid clarity, spot removal and similar moves that can amplify noise (at 2:33-2:58 in the video).","b":false},{"t":"img","f":"v05","w":768,"h":480},{"t":"p","x":"Camera Raw 自带的降噪到底什么水平？Thomas 用 Ctrl+J 复制图层做了个对比：把减少杂色拉满后，很多噪点仍然没有消除，还出现结块现象；继续左滑减少细节，噪点少了，但车牌看不清了、雪地成了一团糊——这也是后面和 Topaz 对比的基础（视频 3:17-4:10 处）。","xe":"How good is Camera Raw's built-in denoise? Thomas duplicated the layer with Ctrl+J for a comparison: with Noise Reduction maxed, plenty of noise survives and starts clumping; dragging Detail further left reduces noise but the license plate becomes unreadable and the snow turns to mush — the baseline for the Topaz comparison later (at 3:17-4:10 in the video).","b":false},{"t":"img","f":"v06","w":768,"h":480},{"t":"h","x":"03 插件核心：模式、滑块与 Auto","xe":"03 Inside the Plugin: Modes, Sliders and Auto"},{"t":"p","x":"正式降噪前建议先复制一个图层——插件会直接在当前图层上应用（视频 4:11 处）。然后通过「滤镜 → Topaz Labs → Denoise AI」进入插件。载入照片后，Remove Noise 和 Sharpen 的默认参数都是 15，对很多照片并不合适，需要逐一调整（4:30-4:48 处）。","xe":"Before the real denoise, duplicate the layer — the plugin applies directly to the active one (at 4:11 in the video). Then enter the plugin via Filter → Topaz Labs → Denoise AI. Once the photo loads, Remove Noise and Sharpen both default to 15, which rarely suits the image, so adjust each one (at 4:30-4:48 in the video).","b":false},{"t":"p","x":"Mode 模式有 Denoise AI 和 AI Clear 两种（视频 4:49 处）。按官网描述优先选 Denoise AI——更好的模型与算法，降噪同时保留更多细节；但针对某些场景它可能完全翻车，此时可以换 AI Clear——更通用的模型，不过细节保护一般，有时会有类似 Camera Raw 的涂抹感（5:01-5:39 处）。","xe":"Mode offers Denoise AI and AI Clear (at 4:49 in the video). Prefer Denoise AI per the official description — a better model that keeps more detail while denoising; but it can fail outright on certain images, in which case switch to AI Clear — a more general model with so-so detail retention and occasional smearing reminiscent of Camera Raw (at 5:01-5:39 in the video).","b":false},{"t":"img","f":"v08","w":768,"h":480},{"t":"p","x":"核心是两个滑块：Remove Noise 越往右降得越狠；Sharpen 补偿降噪损失的锐度（视频 5:40-6:06 处）。但一般来说直接选 Auto：软件会把照片投入深度学习训练出的算法，自动识别画面模式、区分需要保留的细节与需要去除的噪点。这张照片 Auto 给出的是 46 降噪、35 锐化——每张照片的参数都不一样（6:19-6:49 处）。","xe":"The heart is two sliders: Remove Noise, harder to the right; and Sharpen, compensating the sharpness lost to denoising (at 5:40-6:06 in the video). But usually just pick Auto: the software feeds the photo into a deep-learning-trained algorithm that recognizes scene patterns and separates detail to keep from noise to remove. Here Auto suggested 46 noise / 35 sharpen — and the numbers differ for every photo (at 6:19-6:49 in the video).","b":false},{"t":"p","x":"效果非常惊人：车牌号的噪点全部去除，字还恢复出了细节（视频 6:51 处）；人物的羽绒服里反光、褶皱甚至条纹都被识别保留，眼睛鼻子嘴巴也基本恢复（7:22-7:46 处）。它是分区处理的——细节多的区域重点保细节，细节少的区域大幅降噪，这正是普通降噪软件做不到的地方（7:51-8:00 处）。","xe":"The result is startling: the license plate's noise vanishes while the characters regain real detail (at 6:51 in the video); on the person's down jacket, reflections, folds and even stripes are recognized and kept, and the eyes, nose and mouth largely restored (at 7:22-7:46 in the video). It works region by region — guarding detail where there is plenty, denoising hard where there is little — exactly what ordinary denoisers cannot do (at 7:51-8:00 in the video).","b":false},{"t":"img","f":"v09","w":768,"h":480},{"t":"img","f":"v10","w":768,"h":480},{"t":"h","x":"04 微调收尾：锐化、恢复细节与低光模式","xe":"04 Fine-Tuning: Sharpen, Recover Detail, Low Light"},{"t":"p","x":"Auto 之后还可以手动微调：觉得降噪太猛、锐度损失太大，就把 Sharpen 调回去，它控制的是画面边缘的锐化程度，用来克服降噪对边缘的虚化（视频 8:02-8:25 处）。下方的 Post Processing 里还有一个 Recovery Original Detail（恢复原始细节）：滑块拉高会把原图的细节连同部分噪点混回画面（8:26-8:49 处）。","xe":"After Auto you can still fine-tune: if the denoise is too aggressive and sharpness suffers, raise Sharpen, which controls edge sharpening against the blur denoising brings (at 8:02-8:25 in the video). Under Post Processing sits Recovery Original Detail: push the slider and original detail — along with some noise — is mixed back into the image (at 8:26-8:49 in the video).","b":false},{"t":"img","f":"v11","w":768,"h":480},{"t":"p","x":"两者区别要分清：锐化强化边缘，克服降噪的虚化；恢复细节则是把原来的噪点和纹理重新混入，照片更有质感，但也会带回一定噪点（视频 8:52-9:20 处）。Thomas 习惯混回一点点细节——Topaz 降得太干净、一点颗粒都没有反而不真实；而且适当的噪点有色彩平滑、融合细节、缓解色彩断层的作用（9:21-9:56 处）。","xe":"Keep the two apart: Sharpen strengthens edges to counter denoise blur; Recover Original Detail re-mixes original noise and texture, giving the photo more feel — at the cost of some noise (at 8:52-9:20 in the video). Thomas habitually mixes a little back — Topaz can be so clean that a grain-free result looks artificial; and moderate noise actually smooths color, blends detail and eases banding (at 9:21-9:56 in the video).","b":false},{"t":"p","x":"插件下方还有 Color Noise Reduction（颜色降噪）和 Low Light Mode（低光模式），都适合极暗光条件下的照片，尤其是手机暗光直出的 JPEG——暗部往往有五颜六色的色彩噪点，这时打开低光模式会调用专门模型处理（视频 9:58-10:30 处）。但颜色降噪要慎用：它会削弱色彩丰富度，星空照片用它甚至会损失银河的色彩与星系细节（10:34-10:52 处）。","xe":"The plugin also offers Color Noise Reduction and Low Light Mode, both for extreme low-light captures — especially straight-out-of-camera JPEGs from phones at night, whose shadows bristle with multicolored speckle; enabling Low Light Mode calls a dedicated model for exactly that (at 9:58-10:30 in the video). But go easy on Color Noise Reduction: it dulls color richness, and on astro photos it can wipe out the Milky Way's hues and faint nebulae (at 10:34-10:52 in the video).","b":false},{"t":"p","x":"点击右下角 Apply，算法对整张图做深度学习运算（视频 10:54 处）。最终对比：Camera Raw 降噪后噪点依旧惨不忍睹、涂抹感强、锐度严重受损，人物衣服还没降干净；Topaz Denoise AI 则把车牌的字都恢复了出来——天差地别的效果（11:02-11:40 处）。Thomas 也在片尾感谢了最先在 Jeff 流程里分享这个插件的野生动物摄影师 Jeff 老师（11:48 处）。","xe":"Click Apply at the bottom right and the deep-learning engine runs over the whole frame (at 10:54 in the video). The final comparison: after Camera Raw the noise is still a disaster, smeary, with edges badly degraded and the jacket half-treated; Topaz Denoise AI even recovers the characters on the license plate — a difference like night and day (at 11:02-11:40 in the video). Thomas closes by thanking Jeff, the wildlife photographer who first shared the plugin in his workflow (at 11:48 in the video).","b":false},{"t":"img","f":"v12","w":768,"h":480},{"t":"quote","x":"1. 降噪前先在 Camera Raw 恢复曝光、提升阴影，并把减少杂色归零——降噪是后期第一步，锐化是最后一步；2. 优先用 Denoise AI 模式，个别翻车照片再换 AI Clear 兜底；3. 一般直接选 Auto 让算法自动定参，再用 Sharpen 与 Recovery Original Detail 微调边缘与质感；4. 混回一点原始细节和噪点反而更真实，低光直出 JPEG 开低光模式，星空慎用颜色降噪。","xe":"1. In Camera Raw, restore exposure and lift shadows first, and zero out noise reduction — denoise is the first step of editing, sharpening the last; 2. Prefer the Denoise AI model, falling back to AI Clear when it fails on a particular image; 3. Let Auto set the numbers, then fine-tune edges and texture with Sharpen and Recovery Original Detail; 4. Mixing back a touch of original detail and grain reads more natural; enable Low Light Mode for dark JPEGs straight from camera, and go easy on Color Noise Reduction with astro photos."}],"titleEn":"Topaz DeNoise AI Guide: Strong Noise Reduction with Detail Preserved"}